{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T06:38:57Z","timestamp":1776926337445,"version":"3.51.2"},"reference-count":39,"publisher":"Tech Science Press","issue":"3","license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"vor","delay-in-days":214,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.066322","type":"journal-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T03:28:02Z","timestamp":1750735682000},"page":"4825-4849","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Phoneme Labeling in Dysarthric Speech with Digital Twin-Driven Multi-Modal Architecture"],"prefix":"10.32604","volume":"84","author":[{"given":"Saeed","family":"Alzahrani","sequence":"first","affiliation":[]},{"given":"Nazar","family":"Hussain","sequence":"additional","affiliation":[]},{"given":"Farah","family":"Mohammad","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"4278","DOI":"10.3390\/electronics12204278","article-title":"A survey of automatic speech recognition for dysarthric speech","volume":"12","author":"Qian","year":"2023","journal-title":"Electronics"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1038\/nn.2331","article-title":"Maps and streams in the auditory cortex: nonhuman Primates illuminate human speech processing","volume":"12","author":"Rauschecker","year":"2009","journal-title":"Nat Neurosci"},{"key":"ref3","series-title":"Proceedings of the ICASSP, 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"7349","article-title":"End-to-end articulatory modeling for dysarthric articulatory attribute detection","author":"Lin","year":"2020 May 4\u20138"},{"key":"ref4","series-title":"Proceedings of the Interspeech","first-page":"4791","article-title":"Staged knowledge distillation for end-to-end dysarthric speech recognition and speech attribute transcription","author":"Lin","year":"2020 Oct 25\u201329"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/S0021-9924(00)00023-X","article-title":"Research on speech motor control and its disorders: a review and prospective","volume":"33","author":"Kent","year":"2000","journal-title":"J Commun Disord"},{"key":"ref6","series-title":"Proceedings of the 2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","first-page":"42","article-title":"Dysarthric speech augmentation using prosodic transformation and masking for subword end-to-end ASR","author":"Soleymanpour","year":"2021 Oct 13\u201315"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1002\/1531-8257(200101)16:1<79::AID-MDS1013>3.0.CO;2-H","article-title":"Changes in vocal loudness following intensive voice treatment (LSVT) in individuals with Parkinson\u2019s disease: a comparison with untreated patients and normal age-matched controls","volume":"16","author":"Ramig","year":"2001","journal-title":"Mov Disord"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"428","DOI":"10.3390\/app11010428","article-title":"Hierarchical phoneme classification for improved speech recognition","volume":"11","author":"Oh","year":"2021","journal-title":"Appl Sci"},{"key":"ref9","series-title":"Proceedings of the ICASSP, 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6395","article-title":"End-to-end dysarthric speech recognition using multiple databases","author":"Takashima","year":"2019 May 12\u201317"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"e13288","DOI":"10.1111\/exsy.13288","article-title":"A hierarchical automatic phoneme recognition model for Hindi-Devanagari consonants using machine learning technique","volume":"40","author":"Malakar","year":"2023","journal-title":"Expert Syst"},{"key":"ref11","first-page":"379","article-title":"Potentials of telehealth devices for speech therapy in Parkinson\u2019s disease","volume":"18","author":"Beijer","year":"2011","journal-title":"Diagn Rehabil Park Dis"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"119797","DOI":"10.1016\/j.eswa.2023.119797","article-title":"E2E-DASR: end-to-end deep learning-based dysarthric automatic speech recognition","volume":"222","author":"Almadhor","year":"2023","journal-title":"Expert Syst Appl"},{"key":"ref13","series-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing","article-title":"Hmm-based and svm-based recognition of the speech of talkers with spastic dysarthria","author":"Hasegawa-Johnson","year":"2006 May 14\u201319"},{"key":"ref14","series-title":"Proceedings of the 9th International ACM SIGACCESS Conference on Computers and Accessibility","first-page":"255","article-title":"Comparing speaker-dependent and speaker-adaptive acoustic models for recognizing dysarthric speech","author":"Rudzicz","year":"2007 Oct 15\u201317"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"308340","DOI":"10.1155\/2009\/308340","article-title":"Modelling errors in automatic speech recognition for dysarthric speakers","volume":"2009","author":"Caballero Morales","year":"2009","journal-title":"EURASIP J Adv Signal Process"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"2200131","DOI":"10.1002\/aisy.202200131","article-title":"TASTA: text-assisted spatial and temporal attention network for video question answering","volume":"5","author":"Wang","year":"2023","journal-title":"Adv Intell Syst"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"6332","DOI":"10.1007\/s00034-024-02739-6","article-title":"Modeling source and system features through multi-channel convolutional neural network for improving intelligibility assessment of dysarthric speech","volume":"43","author":"Ahmad","year":"2024","journal-title":"Circuits Syst Signal Process"},{"key":"ref18","first-page":"3215","article-title":"Audio-text multimodal speech recognition via dual-tower architecture for mandarin air traffic control communications","volume":"78","author":"Ge","year":"2024","journal-title":"Comput Mater Contin"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"255","DOI":"10.4103\/ijnpnd.ijnpnd_99_23","article-title":"Combined convolution recurrent neural network for the classification of dysarthria speech","volume":"14","author":"Mahendran","year":"2024","journal-title":"Int J Nutr Pharmacol Neurol Dis"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"6227","DOI":"10.3390\/s23136227","article-title":"Evaluating the performance of pre-trained convolutional neural network for audio classification on embedded systems for anomaly detection in smart cities","volume":"23","author":"Lamrini","year":"2023","journal-title":"Sensors"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1007\/s12311-023-01539-z","article-title":"Uncertainty of vowel predictions as a digital biomarker for ataxic dysarthria","volume":"23","author":"Isaev","year":"2024","journal-title":"Cerebellum"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1440986","DOI":"10.3389\/fdgth.2024.1440986","article-title":"An automatic measure for speech intelligibility in dysarthrias-validation across multiple languages and neurological disorders","volume":"6","author":"Tr\u00f6ger","year":"2024","journal-title":"Front Digit Health"},{"key":"ref23","series-title":"Proceedings of the ICASSP, 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2024 Apr 14\u201319; Seoul, Republic of Korea","first-page":"12486","article-title":"Inappropriate pause detection in dysarthric speech using large-scale speech recognition","author":"Lee"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1080\/02699206.2021.2019312","article-title":"Positional asymmetries in consonant production and intelligibility in dysarthric speech","volume":"37","author":"Kim","year":"2023","journal-title":"Clin Linguist Phon"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.specom.2023.02.004","article-title":"Measuring the intelligibility of dysarthric speech through automatic speech recognition in a pluricentric language","volume":"148","author":"Xue","year":"2023","journal-title":"Speech Commun"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"113","DOI":"10.3390\/brainsci13010113","article-title":"Speech and nonspeech parameters in the clinical assessment of dysarthria: a dimensional analysis","volume":"13","author":"Ziegler","year":"2023","journal-title":"Brain Sci"},{"key":"ref27","first-page":"1","article-title":"UTrans-DSR: a hybrid encoder-decoder architecture for dysarthric speech recognition","volume":"2024","author":"Zhang","year":"2024","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"ref28","first-page":"117","article-title":"Speech conversion for dysarthric voice enhancement using fuzzy expectation maximization and diffusion probabilistic models","volume":"26","author":"Liu","year":"2023","journal-title":"Int J Speech Technol"},{"key":"ref29","first-page":"50","article-title":"Data augmentation for automatic speech recognition using dysarthric speech synthesis","volume":"139","author":"Wang","year":"2023","journal-title":"Speech Commun"},{"key":"ref30","unstructured":"Kim H, Lee J. CoLM-DSR: a multimodal approach for dysarthric speech reconstruction with neural codec language modeling. arXiv:2406.08336. 2024."},{"key":"ref31","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1109\/TNSRE.2021.3076778","article-title":"Speech Vision: an end-to-end deep learning-based dysarthric automatic speech recognition system","volume":"29","author":"Shahamiri","year":"2021","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"Lee W, Im S, Do H, Kim Y, Ok J, Lee GG. DyPCL: dynamic phoneme-level contrastive learning for dysarthric speech recognition. arXiv:2501.19010. 2025.","DOI":"10.18653\/v1\/2025.naacl-long.240"},{"key":"ref33","series-title":"Proceedings of the ICASSP, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2023 Jun 4\u201310; Rhodes Island, Greece. Piscataway, NJ, USA","first-page":"1","article-title":"On using the UA-speech and torgo databases to validate automatic dysarthric speech classification approaches","author":"Schu"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"545","DOI":"10.32604\/csse.2023.024450","article-title":"Development of algorithm for person re-identification using extended openface method","volume":"44","author":"Michael Dinesh","year":"2023","journal-title":"Comput Syst Sci Eng"},{"key":"ref35","series-title":"Proceedings of the 2023 34th Irish Signals and Systems Conference (ISSC); 2023 Jun 13\u201314; Dublin, Ireland","first-page":"1","article-title":"Well said: an analysis of the speech characteristics in the LibriSpeech corpus","author":"Debnath"},{"key":"ref36","first-page":"19","article-title":"Research on the recognition and application of Montreal forced aligner for singing audio","volume":"12","author":"Liu","year":"2024","journal-title":"J Comput Electron Inf Manag"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"4951","DOI":"10.1109\/JBHI.2024.3392829","article-title":"Exploring the impact of fine-tuning the wav2vec2 model in database-independent detection of dysarthric speech","volume":"28","author":"Javanmardi","year":"2024","journal-title":"IEEE J Biomed Health Inf"},{"key":"ref38","doi-asserted-by":"crossref","unstructured":"Geng M, Jin Z, Wang T, Hu S, Deng J, Cui M, et al. Use of speech impairment severity for dysarthric speech recognition. arXiv:2305.10659. 2023.","DOI":"10.21437\/Interspeech.2023-322"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"1912","DOI":"10.1109\/TNSRE.2023.3262001","article-title":"Multi-stage audio-visual fusion for dysarthric speech recognition with pre-trained models","volume":"31","author":"Yu","year":"2023","journal-title":"IEEE Trans Neural Syst Rehabil Eng"}],"container-title":["Computers, Materials &amp; Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-84-3\/TSP_CMC_66322\/TSP_CMC_66322.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T05:45:25Z","timestamp":1776923125000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v84n3\/63187"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.066322","relation":{},"ISSN":["1546-2226"],"issn-type":[{"value":"1546-2226","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2025-04-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-30","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-30","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}